© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 104736
    Prev
    Next
    INDEX
    Explanations

    many, much, other, some

    np_acts-logits-general · gemini-2.5-flash-lite

    The main thing this neuron does is detect words expressing quantity, degree, or comparative emphasis.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    當然
    -1.66
    ・・・・・
    -1.59
    If
    -1.54
    はコチラ
    -1.53
    Descubre
    -1.50
    有什麼
    -1.48
    の詳細
    -1.47
    连连
    -1.42
    を選
    -1.42
    Here
    -1.42
    POSITIVE LOGITS
     and
    1.81
     for
    1.51
     so
    1.46
    @[+][
    1.45
    高原
    1.45
    ╔
    1.41
    NUC
    1.38
    errorCode
    1.38
    ’?
    1.35
     แต่
    1.33
    Activations Density 0.009%

    No Known Activations